Fast Modelling Algorithm for Realistic Three-Dimensional Human Face for Film and Television Animation

Limin Xu,Zhihan Lv

doi:10.1155/2021/3346136

Abstract

Aiming at the face photos of film and television animation, this paper proposes a new fast three-dimensional (3D) face modelling algorithm. First of all, based on the LBF algorithm, this paper proposes a multifeature selection idea to automatically detect multiple features of the face. Secondly, in order to solve the shortcomings of slow training speed while achieving large pose face alignment, the regression-based CNN is selected as the algorithm to achieve fast convergence. Then, due to the influence of various factors, the extracted feature points are not completely correct, and Gabor features are used to screen the matching of feature points. Finally, by analysing the principle of 3DMM 3D face reconstruction, a single-view 3D face reconstruction method based on CNN is proposed. The experimental results show that the algorithm in this paper has good reconstruction performance and real-time performance and can realize the rapid modelling of human face.

Highlights

Human face is a very important communication channel for human beings, and it is the carrier of human’s complex expressions and language such as happiness, anger, sorrow, and happiness
With the development of technologies such as computer graphics and virtual reality, especially the emergence of virtual announcers, research based on the design of virtual characters has been widely valued. e human face contains a large amount of characteristic information, which is the most important organ for distinguishing human beings. e computer simulation study of a specific human face is of great significance. 3D face models play an important role in applications such as film and television production, computer games, distance education, medical beauty, and intelligent recognition [5,6,7]
In order to solve the shortcomings of slow training speed while achieving large pose face alignment, the regression-based CNN is selected as the algorithm to achieve fast convergence

Summary

Introduction

Human face is a very important communication channel for human beings, and it is the carrier of human’s complex expressions and language such as happiness, anger, sorrow, and happiness. Realistic 3D face modelling has been a research hotspot in the field of computer vision and computer graphics for nearly 30 years, and it has a wide range of applications in film and television animation, human-computer interaction, video games, and communications [3, 4]. 3D face models play an important role in applications such as film and television production, computer games, distance education, medical beauty, and intelligent recognition [5,6,7]. Based on the LBF algorithm, a multifeature selection idea is proposed to automatically detect multiple features of the face. In order to solve the shortcomings of slow training speed while achieving large pose face alignment, the regression-based CNN is selected as the algorithm to achieve fast convergence

Methods

Results

Conclusion